Web & Frontend
Web development agent skills handle frontend and full-stack work: component patterns, CSS and accessibility fixes, performance budgets, and framework conventions. Install a skill once and your AI agent follows the same playbook in every project, from quick prototypes to production apps.
-
aayushms Skill Scan ProjectUse this skill when the user asks to "scan my project", "analyze my project", "what does my project need to run", "find all services in my project", "document how to run my project", "understand my project structure", "detect services in my codebase", "what frameworks does my project use", "analyze my codebase for deployment", or when invoked by the deploy-project orchestrator as the first step before deployment. This skill reads the project codebase, detects all services (frontend, backend, database, queues, workers), recommends free deployment platforms for each service, and writes three documentation files to DEPLOYMENT_DOCS/.
-
aayushms Skill Deploy VercelDeploy frontend applications to Vercel using CLI and REST API. Use when the user wants to deploy a React, Vite, Next.js, or static frontend to Vercel. Triggers on "deploy to Vercel", "Vercel deploy", "host my frontend", "deploy my app to Vercel", or any task requiring Vercel project creation, environment variables, production deployment, or GitHub auto-deploy connection.
-
aayushms Skill Verify DeploymentUse this skill when the user asks to "verify my deployment", "check if everything is working", "test my deployment", "check if my services are up", "run health checks", or when invoked by deploy-project as the final step after CI/CD setup. Reads DEPLOYMENT_DOCS/DEPLOYED_ENV.md for service URLs, runs HTTP health checks on all services, uses agent-browser to visually verify the frontend loads, tests cross-service connectivity (frontend calls backend, backend connects to DB), and prints a pass/fail summary table. Retries Render backend endpoints up to 3 times due to free tier cold starts.
-
rijul1204 Bundle HTML OutputConvert the current plan, spec, design doc, or conversation context into a single self-contained, share-able HTML file with rich visual structure (tables, SVG diagrams, code blocks, responsive layout, in-page navigation). Supports four output shapes — editorial, technical-doc, dashboard, and slide-deck. Use when the user invokes /html-output, asks to "export as HTML", "render this as HTML", "structure your response as HTML" (Karpathy-style), "make a web version", "share this as a link", "present this as slides / a slideshow / a deck", or wants a long plan or spec converted from markdown into something visually scannable or presentable.
-
cdxiaodong Skill XssXSS 测试技能 —— 面向真实业务系统,区分渲染上下文(HTML/属性/JS/CSS/URL),覆盖存储型/反射型/DOM 型,对抗 CSP 与输入过滤,产出可复现 PoC
-
plimeor Bundle Create HTML ArtifactProduce a single portable local HTML file as the final deliverable — a report, doc, dashboard, landing page, demo, tool, or presentation rendered as one .html that opens straight from disk. Use when the user asks for an HTML page/file/artifact saved locally, a visual or interactive deliverable as a standalone web page, or when porting content into one HTML file. Not for publishing or hosting a page online — the deliverable is a local file, never a URL — and not for multi-file web projects or apps with a build step.
-
zxhfighter Bundle God Component DetectorDetects God Components (components with too many responsibilities, mixing UI/business logic/side effects, excessive line count). Use when reviewing React/Next.js components for architecture issues, refactoring opportunities, or code quality assessments.
-
cyl19970726 Bundle Webar Mindar IOSBuild, debug, and ship browser-based AR image-tracking experiences (MindAR + A-Frame + Three.js inside a Next.js App Router H5), and especially diagnose the iOS-Safari/WebKit-only failures that desktop Chromium never reproduces — blank or black camera after "start AR", scenes collapsing to width:0, next/image not rendering, gyro/DeviceOrientation not firing. Use this whenever the task involves WebAR / MindAR / A-Frame / image-tracking / "扫描识别" AR on phones, an AR page that works in Chrome but is blank/broken on iPhone, reproducing iOS WebKit bugs without a physical device, or deploying such an app to a GCE VM behind a cloudflare quick tunnel for on-phone testing. Reach for it even when the user just says "the camera is blank on iPhone after I tap start" or "make the AR camera fullscreen" — the iOS-WebKit gotchas and the Playwright-WebKit verification combo here save hours of guess-and-redeploy.
-
cyl19970726 Bundle Ar 3d Animation Pipeline从 0 到 1 制作浏览器 WebAR 的 3D 动画角色/场景的完整流程、技术原理与已验证工具链。 当任务涉及"把一个 IP 形象/吉祥物做成「扫描识别卡或冰箱贴 → 3D 角色临现并做动作(倒茶/挥手/提灯等)」的 AR 体验", 或需要:概念图(art direction)定调、AI 图生3D(Tripo/TRELLIS)、给 Q版角色自动绑骨(Mixamo)、 移动端模型优化(gltf-transform meshopt)、react-three-fiber 场景装配、手作骨骼动画、 给程序化动画做客观精度评估(几何 + 视觉 agent 双评估)、MindAR 图像追踪接入、AR 资产部署真机 —— 时, 务必使用本 skill。涉及 codex/FLUX 生成对版参照图、Tripo API 自动建模绑骨、TRELLIS、rembg 抠图、 GLB 减面压缩、骨骼蒙皮、扫贴/识别卡 AR、3D 吉祥物动起来、AR 冰箱贴 等关键词时也应触发, 即使用户没明说"流程"或"skill"。
-
inspirepan Skill UI MockupGenerate polished UI mockup images for apps, websites, dashboards, landing pages, SaaS tools, mobile screens, live-commerce screens, and product interface concepts. Use when the user asks for UI mockup, app screen, website concept, dashboard visual, landing page image, 产品界面, 应用界面, 后台仪表盘, or 直播间界面. Do NOT use for production React code, wireframe-only planning, product photography, article covers, posters, or dense knowledge infographics.
-
lufigir Skill GrillingGrill the user relentlessly about a plan, decision, or idea until you both reach a shared understanding. You MUST use this before any creative work — building a feature, adding functionality, changing behaviour, designing a component — and before entering plan mode. Also use when the user wants to stress-test their thinking, or on any 'grill' trigger phrase. Spanish triggers: "vamos a hacer", "vamos a armar", "vamos a construir", "quiero hacer/armar/construir", "necesito que", "hay que agregar", "podemos hacer", "grilléame", "interrógame", "pregúntame lo que necesites", "cuestióname".
-
lufigir Bundle Improve Codebase ArchitectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
-
minhuw Skill AccessibilityPrimary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help dialogs, accessible views, verbosity settings, signals, ARIA announcements, keyboard navigation, and ARIA labels/roles.
-
minhuw Skill UX CSS LayoutVS Code CSS conventions, file organization, class naming, standard sizes, SplitView/Grid layout, scrollable content, responsive layout, and text overflow/ellipsis patterns. Use when writing CSS, building layouts, or fixing text truncation issues.
-
minhuw Skill Update ScreenshotsUpdate the committed blocks-ci screenshot hashes after the "Screenshots & Tests" check fails, or investigate a screenshot diff reported on a PR. Use when asked to update, accept, or refresh component screenshot baselines from CI. This skill should be run as a subagent.
-
minhuw Skill Validate UI ScenarioUse when reproducing a UI bug or verifying a fix by driving a real VS Code window end to end and capturing evidence. Writes a scenario file, runs it against a dev build or installed Insiders, and produces a captioned video, per-step screenshots, a Playwright trace, and an HTML report to attach to an issue or pull request.
-
twominutereports Bundle Tmr Meta Ads AuditRuns a comprehensive Meta / Facebook Ads account audit using live data from Two Minute Reports (TMR) MCP. Trigger this skill whenever the user says anything like: "audit my Meta Ads", "audit my Facebook Ads", "review my Facebook campaigns", "analyze my Meta ad account", "why is my ROAS dropping on Facebook", "Meta ads health check", "Facebook ads report", "creative fatigue audit", "check my ad sets", "Facebook wasted spend", "what's wrong with my Meta campaigns", "review my audiences", "placement audit Facebook", or any request to evaluate, score, diagnose, or improve a Meta / Facebook Ads account. Produces a rich HTML audit report with visual scorecards, ranked tables, creative fatigue signals, audience analysis, placement breakdown, and a prioritized action plan — all with expert commentary. IMPORTANT: Always use Two Minute Reports MCP to fetch live data. Never ask the user to upload files or paste data.
-
twominutereports Bundle Tmr Google Ads AuditRuns a comprehensive Google Ads account audit using live data from Two Minute Reports (TMR) MCP. Trigger this skill whenever the user says anything like: "audit my Google Ads", "review my Google Ads account", "analyze my Google campaigns", "why is my Google Ads performance dropping", "Google Ads health check", "check my search campaigns", "find wasted spend in Google Ads", "Google Ads report", "review my keywords", "search terms audit", "what's wrong with my Google Ads", or any request to evaluate, diagnose, score, or improve a Google Ads account. Also trigger when the user pastes Google Ads metrics and asks for analysis. Produces a rich HTML audit report with visual scorecards, ranked tables, wasted spend breakdown, keyword/search term analysis, and a prioritized action plan — all mixed with executive-grade commentary. IMPORTANT: Always use Two Minute Reports MCP to fetch live data. Never ask the user to upload files or paste data manually.
-
just-silver Skill BootstrapblazorUse when working with BootstrapBlazor (also called BB, bb, or bootstrapblazor) components and needing their parameters, events, or public methods — e.g. before writing or modifying Razor/C# code that depends on a BB component API (Table, Dialog, Upload, etc.), or when unsure whether a BB API exists or what its exact name/signature is. Get official docs via the bb-llms CLI; never invent APIs from memory.
-
mjunaidca Bundle Quiz GeneratorALWAYS generate interactive quizzes using the Quiz component (50 comprehensive questions total). Generates 50 college-level conceptual questions with immediate feedback per question. Quiz component automatically displays 15-20 questions per batch, randomized each retake. Features: immediate feedback after each answer (correct option + explanation + why wrong if incorrect), automatic batch shuffling on retake, no passing/failing threshold, color-coded feedback, theme support. Globally-registered Quiz component handles all UI/UX. Follows ##_chapter_##_quiz.md naming convention. INCLUDES: Automated answer redistribution with intelligent explanation regeneration (consolidates quiz-answer-redistributor functionality).
-
yonatangross Bundle Performance OptimizationFull-stack performance analysis, optimization patterns, monitoring strategies, React 19 concurrent features, and bundle analysis for 2025+ development
-
gcwing Skill Product App SurfaceProduct App surface development guidance. Use when creating, editing, reviewing, or validating an app-private surface, including Product App UI entrypoints, source/index.html, style.css, ui.js, worker.js coordination, primary surface behavior, runtime preview, and user-path evidence.
-
gcwing Skill Product App Tool ComponentProduct App Tool Component development guidance. Use when creating, editing, reviewing, or validating an app-private Tool Component, including source/tool.schema.json, source/tool.js, structured tool contracts, app or agent calls, deterministic outputs, and capability evidence.
-
gcwing Skill Product App Agent ComponentProduct App Agent Component development guidance. Use when creating, editing, reviewing, or validating an app-private Agent Component, including the app's built-in associated agent, prompt.md, fixtures.json, AI behavior, backend bindings, service actions, and Agent Eval evidence.
-
gcwing Skill Product App Skill ComponentProduct App Skill Component development guidance. Use when creating, editing, reviewing, or validating an app-private Skill Component, including app-specific workflow knowledge, source/SKILL.md, reusable guidance for the app's agent or authoring flow, examples, and validation evidence.
-
gcwing Skill Product App Bridge ComponentProduct App Bridge Component development guidance. Use when creating, editing, reviewing, or validating an app-private Bridge Component, including service action boundaries, source/actions.json, source/worker.js, backend bindings, host or external capability access, permissions, and capability preview evidence.
-
gcwing Skill Product App Runtime ComponentProduct App Runtime Component development guidance. Use when creating, editing, reviewing, or validating an app-private Runtime Component, including special Product App hosting requirements, source/runtime.json, execution host boundaries, runtime definition changes, and runtime validation evidence.
-
igniteui Bundle Igniteui Angular ComponentsCovers all non-grid Ignite UI for Angular UI components: application scaffolding and setup, form controls (inputs, combos, selects, date/time pickers, calendar, checkbox, radio, switch, slider), layout containers (tabs, stepper, accordion, splitter, navigation drawer), data-display components (list, tree, card, chips, carousel, paginator, progress indicators, chat), feedback overlays (dialog, snackbar, toast, banner), directives (button, icon button, button group, ripple, tooltip, drag-and-drop), Dock Manager, Layout Manager, Tile Manager, and Charts. Use when users ask about any Ignite UI Angular component that is NOT a data grid — such as forms, dropdowns, pickers, dialogs, navigation, lists, trees, cards, charts, or initial project setup. Do NOT use for data grids, tables, or tabular data — use igniteui-angular-grids instead. Do NOT use for theming or styling — use igniteui-angular-theming instead.
-
igniteui Bundle Igniteui React ComponentsThis skill identifies the right Ignite UI for React components for any UI pattern and covers installing, importing, and using them — including JSX patterns, event handling, refs, forms, and TypeScript. Use this when choosing components, setting up a React project, writing component JSX, handling events, or integrating with React state and form libraries.
-
igniteui Bundle Igniteui React Customize ThemeThis skill customizes Ignite UI for React component styling using CSS custom properties and the full theming system and should be used when applying brand colors, dark mode, component-level overrides, or scoped themes in a React application
-
igniteui Skill Igniteui React Optimize Bundle SizeThis skill optimizes application bundle size when using Ignite UI for React and should be used when the bundle is too large, when setting up tree-shaking, or when lazy loading heavy components like grids and charts
-
igniteui Bundle Igniteui React Generate From Image DesignImplement React application views from design images using Ignite UI for React components. Uses MCP servers (igniteui-cli, igniteui-theming) and tools for component discovery, docs lookup, and theming to choose components, generate theme tokens, and follow React-specific best practices. Triggers when the user provides a design image (screenshot, mockup, wireframe) and wants it built as a working React view with Ignite UI for React. Also triggers when the user asks to "implement this design", "build this UI", "convert this mockup", or "create a page from this image" in an Ignite UI React project.
-
igniteui Bundle Igniteui Wc Integrate With FrameworkIntegrate Ignite UI Web Components packages into React, Angular, Vue, or vanilla JS applications with framework-specific configurations
-
igniteui Skill Igniteui Wc Customize Component ThemeCustomize Ignite UI Web Components styling using CSS custom properties, optional Sass, and the igniteui-theming MCP server for AI-assisted theming
-
opensearch-project Skill Implement FeatureGuided feature implementation for Agent Health. Use when a user wants to add a new capability, endpoint, CLI command, or UI component to the Agent Health project. Ensures correct architecture layer, coding conventions, test coverage, and PR readiness.
-
sonhaicoder Bundle Code ReviewCode review skill — find bugs, security issues, anti-patterns BEFORE merge. AUTO-TRIGGER khi: user nói "review/check code/audit/PR review", file vừa changed (git diff), Claude Code spawn reviewer/qa-reviewer agent, hoặc trước khi commit/push. Force apply 6 audit lenses: (1) Security (SQLi/XSS/secrets/auth bypass), (2) Multi-tenant leak (shop_id missing), (3) Money precision (float vs Decimal), (4) Race conditions (read-then-write), (5) State machine violations (order/payment status jumps), (6) API↔frontend boundary mismatch. Plus 27 anti-patterns + 5-dim severity scoring + grep recipes ready-to-run. Distilled từ Commerce Platform 100 commits production patterns. KHÔNG dùng cho: writing new code (use feature skill), planning/architecture (use planner).
Frequently asked questions
What are Web & Frontend agent skills?
Web development agent skills handle frontend and full-stack work: component patterns, CSS and accessibility fixes, performance budgets, and framework conventions. Install a skill once and your AI agent follows the same playbook in every project, from quick prototypes to production apps.
Which Web & Frontend skills are most installed?
Popular Web & Frontend skills on SkillMD right now include create-html-artifact, bootstrapblazor, igniteui-react-generate-from-image-design. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Web & Frontend skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.